abcorrea/random-v3

adapter_config.json

@@ -28,13 +28,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj",
-    "o_proj",
-    "k_proj",
     "gate_proj",
+    "up_proj",
+    "k_proj",
     "down_proj",
-    "up_proj"
+    "q_proj",
+    "o_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6c91a6714fbadc95b6bc343452fbde8517dc1a74d2414da157e973e3936bbd8
+oid sha256:d3eb406ed9b5979bf1b06412fe1f02dc9ca16c0622e74eaca7d3c406b5ca0b2c
 size 1688012760

tokenizer_config.json

@@ -231,7 +231,7 @@
   "eos_token": "<|im_end|>",
   "errors": "replace",
   "extra_special_tokens": {},
-  "model_max_length": 32768,
+  "model_max_length": 262144,
   "pad_token": "<|endoftext|>",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0b530780a2995c276eb8247f21af59e99a73a8cbee76d2b382b25b21c62a786
+oid sha256:7e6da49631f326d78f32d67927c75da93dcc049780c6e0edb6deb15d70962a2a
 size 6161